Back to loops
Docsmanual triggerhook-bundle-ready Hardened

Claude Code Hooks Setup

A setup loop for teams adopting Claude Code hooks without shipping unsafe or noisy automation.

Use loop copies the kickoff prompt. Copy Markdown and Download loop include the complete Markdown page with context, source attribution, anchors, and guardrails. Cursor / Claude Code buttons prepare the shorter kickoff prompt only.

Run shape

Supported agents

Claude Code

Goal

Design Claude Code hooks that improve safety without blocking legitimate work.

Feedback gate

rg -n "hooks|PostToolUse|PreToolUse|Stop" .claude AGENTS.md CLAUDE.md

Stop condition

Hook behavior is documented, scoped, safe, and testable.

Do not weaken, skip, delete, or rewrite the validation command to force success.
Do not claim completion until the stated exit condition is actually satisfied.
If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
Required context

Give the agent these inputs before it starts the loop. This keeps discovery bounded and prevents vague retries.

Desired hook events.
Allowed commands.
Project verification policy.
Required tools

The loop assumes these commands or integrations are available. Missing tools should be reported as blockers, not ignored.

Claude Code
project verification commands
How to run

Two separate pieces: the kickoff prompt starts the loop, while the downloaded Markdown carries the complete reference page.

1. Copy or download

Use the kickoff for a fast agent run. Download the full Markdown when you need source, context, and attribution in one file.

2. Paste into the agent

Start a fresh agent session in the target repo and provide the requested project context if the loop asks for it.

3. Let it self-pace

The agent should act, check evidence, retry only when the gate fails, and stop at the stated exit condition.

manual triggerDocs Step flow
Manual start
Define hook goals
Map commands to risks
Draft hook config
Test manually first
Feedback gate
Hook behavior is documented, scoped, safe, and testable.
not done → return to next actiondone → exit condition met
Manual startDefine hook goalsMap commands to risksDraft hook configTest manually firstFeedback gatedoneHook behavior is documented, scoped, safe, and testable.not done
Action checklist

The diagram shows the order. This checklist keeps only the action, command, and failure handling needed during a real pass.

1. Define hook goals

Choose which events need automation and why.

2. Map commands to risks

Classify safe read-only commands vs write/destructive commands.

3. Draft hook config

Prepare hook behavior or documentation without blindly enabling it.

4. Test manually first

Run commands outside hooks before enabling automation.

Kickoff prompt

This is the text copied by Use loop. It is intentionally shorter than the Markdown export.

Design Claude Code hooks for this repository. Define hook goals, allowed commands, risks, and manual verification before enabling them.
Goal: Design Claude Code hooks that improve safety without blocking legitimate work.
Check command: rg -n "hooks|PostToolUse|PreToolUse|Stop" .claude AGENTS.md CLAUDE.md
Exit condition: Hook behavior is documented, scoped, safe, and testable.
Max iterations: 3
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not enable hooks that run destructive commands without explicit human approval.

Quality

84/100

Safety

88/100

Expected output

Hook plan with event, command, risk, and test strategy.

Related loops

Browse all
Testingevent trigger Hardened

Post-Edit Test Guard

After code edits, detect the affected surface and run the closest relevant validation before declaring completion.

CursorClaude CodeCodex
post-edittestsguard

Kickoff preview

After every code edit, list changed files, choose the closest meaningful validation, run it, and report evidence before claiming completion.
Goal: Run the closest meaningful verification after edits and report evidence.
Check command: git diff --name-only HEAD
Exit condition: Relevant validation has been run and either passes or failures are reported with evidence.
Max iterations: 4
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not say “not run” without explaining why no meaningful check exists.
View
Securityevent trigger Hardened

Pre-Commit Guard

Before committing, run diff hygiene, secrets checks, and the closest validation command.

Claude CodeCodexGemini CLIOpenCode
pre-commitsecuritygit

Kickoff preview

Before committing, inspect the staged diff, scan for secrets/debug flags, run relevant validation, and only commit if the guard passes.
Goal: Block commits that contain secrets, debug switches, or unverified broken code.
Check command: git diff --cached --check
Exit condition: Staged diff is clean, no obvious secrets/debug flags are present, and relevant validation passes or is explained.
Max iterations: 3
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not commit secrets, local env files, debug flags, or generated private artifacts.
View
Docsmanual trigger Hardened

AGENTS.md Improvement Loop

Audit and improve repository agent instructions so future AI sessions follow project conventions and verification rules.

Claude CodeCodexCursor
agents-mdproject-contextinstructions

Kickoff preview

Audit repository agent instructions against actual project files, then improve them with accurate commands, architecture rules, and verification expectations.
Goal: Make repository instructions accurate, actionable, and verification-oriented.
Check command: ls -la && rg -n "build|test|lint|deploy" README.md package.json AGENTS.md CLAUDE.md
Exit condition: Agent instructions state stack, commands, architecture rules, and verification expectations accurately.
Max iterations: 3
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not invent commands, tools, or architecture claims that are not present in the repository.
View
CImanual trigger Hardened

Ship PR Until Green

Implement a scoped change, open or update a pull request, inspect CI, and continue until all required PR checks pass.

CursorClaude CodeCodex
pull-requestcigithub-actionsverification

Kickoff preview

Take this branch to a green pull request. Implement the requested change, run local verification, open or update the PR, run `gh pr checks`, inspect failures, fix root causes, and repeat until every required check passes or you hit the iteration cap.
Goal: Open or update a pull request and stop only when all required PR checks are green.
Check command: gh pr checks
Exit condition: All required pull request checks are successful and the PR is ready for review or merge.
Max iterations: 10
Guardrails:
- Do not weaken, skip, delete, or rewrite the validation command to force success.
- Do not claim completion until the stated exit condition is actually satisfied.
- If blocked, report the blocker, evidence, and next safest action instead of gaming the metric.
- Do not disable required checks, edit loops to skip jobs, or remove tests to make CI green.
- Do not merge the PR unless the user explicitly asked for merge authority.
View